© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47367
    Prev
    Next
    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roche
    -0.08
    Routes
    -0.08
    Oid
    -0.07
    Lic
    -0.07
    taj
    -0.07
    Everybody
    -0.07
    Admissions
    -0.07
    formations
    -0.07
     domicile
    -0.07
    Feder
    -0.07
    POSITIVE LOGITS
    вае
    0.08
    inne
    0.08
     kump
    0.08
     Pops
    0.07
     krijgen
    0.07
    ści
    0.07
     verilen
    0.07
     sek
    0.07
     Brabant
    0.07
    idas
    0.07
    Activations Density 0.013%

    No Known Activations